Software Engineer II - Cloud-Native Agent Harness (Mecatl)

Stacklok is led by CEO Craig McLuckie and CTO Joe Beda, two of the creators of Kubernetes. Kubernetes helped give enterprises more freedom over where and how they run software. Now we're bringing that same open approach to AI agents.

As AI agents take on more autonomous, long-running work, enterprises need infrastructure to run them securely and reliably at scale, without giving up control of their data, systems, or models. We're building open, Kubernetes-native infrastructure that brings together agent execution, secure access to tools and systems, and centralized controls for identity, permissions, and policy. This is an opportunity to help shape a foundational layer for enterprise AI while the architecture is still being defined.

We build in the open alongside the community. Our open source projects include ToolHive, an MCP platform that secures more than 20 million tool calls each month, and Mecatl, a cloud-native agent harness. Our commercial offering, Stacklok Enterprise, extends these capabilities with an AI gateway, centralized identity, policy enforcement, and observability.

Location

This is a remote role based in North America, with a strong preference for candidates located in the U.S. Eastern Time Zone. 

The Opportunity

AI agents are moving into production, and the harness that runs them is becoming critical infrastructure. Enterprises need that harness to be secure, auditable, and portable across models, clients, and deployment environments. Mecatl is Stacklok's open source, cloud-native agent harness. It provides the agent loop, tools, permissions, hooks, delegation, and durable sessions for running agents as production workloads on infrastructure you operate.

As a Software Engineer II on the Mecatl team, you will build the platform that agents run on, and you will build it with agents. This is a hands-on role with real independence. You will deliver features and fixes across the engine, the Kubernetes-native runtime, the client surfaces (gRPC, HTTP/SSE, the TypeScript SDK, and the terminal client), and the permission and governance layers that make agent behavior safe to trust. You will go deep in one area while developing a system-wide understanding of how the harness fits together.

We are also an AI-first engineering team. We use agents throughout our own development lifecycle, and we are still working out what good looks like. Your own experiments, and what you learn from them, will feed directly into how the team works.

What Success Looks Like: First 3-6 Months

• Ramped quickly on the Mecatl codebase and its development process, and began contributing independently without needing close guidance.
  
  
• Shipped your first features and fixes within the first few months, then delivered core harness work consistently thereafter.
  
  
• Owned a product-minded improvement end to end, from understanding how people use Mecatl to shipping a change and learning from the result.
  
  
• Contributed a concrete improvement to how the team uses AI in development, such as a workflow, evaluation, guardrail, or measurement approach that the team adopted.
  
  
• Strengthened the team and community by reviewing pull requests thoughtfully, including AI-assisted changes, and helping open source users get more from Mecatl.

In This Role, You Will

• Build and deliver features in the open across Mecatl, including the agent loop, tool and permission systems, session and state management, the Kubernetes runtime, and client SDKs.
  
  
• Fix bugs and harden the harness for production use, improving reliability, security, and observability.
  
  
• Write testable, readable code that accounts for edge cases and error handling, produce clear design docs for the work you take on, and review pull requests, including AI-assisted changes.
  
  
• Understand outcomes and partner with the team anchor to break down the work. Escalate decisions to product or staff engineers as needed. 
  
  
• Use AI agents as a core part of your own workflow, and bring a critical eye to what they produce: review it, test it, and own it.
  
  
• Find where your AI workflow breaks down on Mecatl work, experiment to fix it, and bring structured findings back so the team gets faster and better, not just busier.
  
  
• Apply security judgment to AI-assisted development, including permissions, secrets handling, untrusted content, and the limits of what an agent should be trusted to do.

Desired Skill & Experience

We do not expect every candidate to meet every point below. If this role excites you and you bring most of it, we encourage you to apply.

• Proficiency in Go, writing clean, testable code that accounts for edge cases and error handling, plus clear design docs and thoughtful code reviews.
  
  
• Demonstrated ability to deliver features independently across a backend or platform codebase, from implementation through testing and into a release.
  
  
• Working knowledge of distributed systems and cloud-native infrastructure, such as Kubernetes, containers, and service APIs (gRPC or HTTP). Experience with durable state, concurrency, or streaming is a plus.
  
  
• A personal AI-assisted development workflow you can walk through, with a clear sense of where it helps, where it breaks, and its risks, such as prompt injection and excessive agent permissions.
  
  
• Interest in agent infrastructure, such as agent loops, tool use, MCP, model providers, or evaluation. Prior experience building on or contributing to an AI platform or open source project is a plus.
  
  
• Ideally, a product engineering mindset: curious about users and their problems, comfortable questioning requirements, and motivated by shipping something people use.
  
  
• AI-first mindset: builds AI into the development workflow to accelerate delivery, improve the quality of what ships, and rethink how problems get solved.
  
  
• Communication: excellent written and verbal communication, able to explain complex technical ideas clearly to technical and non-technical audiences.
  
  
• Startup mentality and intrinsic motivation: self-directed and hands-on, thrives in fast-moving, ambiguous environments, and drives clarity through action.
  
  
  

Compensation: The anticipated base salary range for this position is $157,500 - $192,500. In addition to base salary, this role offers equity and a comprehensive benefits package.

#LI-Remote

Why Join Us?

At Stacklok, we believe great technology is built by teams that support, challenge, and inspire one another. We are AI maximalists, confident in AI’s potential and committed to building technology people can trust. We use AI in our own work and experiment openly.

You’ll build alongside people with deep experience in open source, cloud-native technologies, security, and developer tools. We stay close to customers, use our own products, and share what we learn to keep improving. You’ll have room to make decisions, support when you need it, and teammates who push themselves to do their best work.

We offer competitive compensation and equity, comprehensive medical, dental, and vision coverage, and a flexible hybrid or remote work environment. Our benefits include flexible PTO, paid holidays, and paid parental leave, along with team offsites to collaborate and connect in person.

If you’re excited about what we’re building and want to work with people who care about their craft, community, and each other, we’d love to hear from you.

--

Stacklok Inc, is proud to be an equal opportunity employer. We are committed to providing equal employment opportunities for all people and place great value in both diversity and inclusiveness. All qualified applicants will be considered for employment without regard to their, or any other person's, perceived or actual race, color, religion, sex, gender, gender identity, gender expression, sexual orientation, national origin, ancestry, citizenship, age, physical or mental disability, medical condition, family care status, or any other basis protected by law.